Ask HN: What is the weirdest or most surreal recent technology you have seen?

If you're not in the bio field, you may not be aware just how routine genetic modification has become. For the larger companies, projects can involve thousands of different iterations on DNA sequences, all of which are created, put in a cell, grown, sequenced, and analyzed. It's absolutely routine at this point - it's not a science or even engineering challenge project it's an operations project.

The one that really freaked me out, though, was learning about organoids - lab-grown clusters of organ cells used to research the effects of genetic disorders. Liver, kidney, and heart organoids are fine, but these are also used to study brain disorders, in which brain organoids - clusters of neurons - are grown from the stem cells of affected individuals. These clusters of neurons have been known to start firing and even display synchronized patterns...

If I were to restart my career, this is likely the field I'd pursue. I read The Gene: An Intimate History by Siddhartha Mukherjee last year and just became enraptured in the possibilities.

I'm wondering if there's anything I can contribute to that field as someone with general programming capabilities.

> I'm wondering if there's anything I can contribute to that field as someone with general programming capabilities.

Oh there Absolutely is!

In general, there are four really high impact areas for computer folks - automation of lab equipment allows for scaling the number of experiments and the data that can be gathered by orders of magnitude; data science and engineering to sort, catalog, and investigate that data; building and scaling scientific computing systems to run analysis repeatably at scale; and even standard application building to manage and improve the overall process of tracking experiments and coordinating between groups.

The scientists and bioinformatics folks are very good at what they do, but someone who really understands how to build, manage, and scale software systems is an enormous force multiplier. If you're interested in the field, I really strongly recommend it.

Except somehow the required education is much higher and the pay is much worse than software, right?

I’m personally surprised we don’t have 20x as many people working in biotech.

I just finished that book, it was really good. I can't wait to read The Song of the Cell.

Maybe not weird or surreal enough for HN. But I am amazed by the stability and quality of videos from my drone.

It's just amazing that I could easily fly a kilometer away whilst having a live feed of the footage being streamed back to my controller.

I have a sub 250g drone, so it's so light yet easily able to withstand pretty strong winds and the videos look great on a big 4K TV afterwards!

It seems like every amateur or even personal production has these big beautiful sweeping aerial shots now, when 10 years ago it would be only available to medium size productions that could rent a commercial drone, and 20 years ago only available to large productions that could afford to rent a helicopter.

I do a lot of kayaking (not white water kayaking) and fishing off my kayak in lakes, rivers, and the ocean on calmer days.

Does your style drone have any following features? Looking for something to fly around looking for fish and something that will follow me or do fly-bys when I’m doing something with the family.

I thought about that too and they are all not watertight. There are Swellpros that are, but they are not hobby drones. And their specs are no match to current hobby drones.

I have a DJI Mini 3 Pro, it has a feature called Active Track[0] where you highlight a subject on the screen and then select how you'd like it to follow you. It can go alongside you or behind you - can follow things like cars too. Despite the sensors, it can be a little scary getting it to follow you when there are trees or telephone lines nearby, but in a lake or the sea it should be great. There are safety features where if it loses connection to the controller it can hover in place, land or return to home (where it took off from).

[0] - https://store.dji.com/guides/film-like-a-pro-with-activetrac...

I think Skydio has the best autonomous follow feature I’ve seen so far.

Yeah, the DJI Mini 3 Pro is that drone... get the basic controller version.

in some form, this was present on DJI drones even 2 generations ago

Not OP but Skydio might have the drones you need?

DJI is a juggernaut and i imagine will catch up, but when i last looked about a year ago Skydio autonomous tracking was dramatically better. It was the first thing that popped into mind when reading that question.

Yeah, I have insurance with 'Flyaway Coverage'. Still have to pay a fee and there's a limit to the number of claims you can make over a time period but it's a lot cheaper than buying a new drone.

Wow how much is it? Where do you buy it? Is it worth it for a sub $500 drone?

It's a DJI Mini 3 Pro. Never had any experiences with other drones, so can't compare it to others - but I love it!

The new DJI Mini 3 does look good too if you're on more of a budget.

Magnetic resonance focused high intensity ultrasound to open the blood-brain barrier in humans to deliver drugs directly to brain tissue - https://www.nature.com/articles/s41467-019-12426-9

This is interesting to me because my mother has MS and it's _because_ the blood-brain barrier is too open that she has health issues. Surprising there's good reason to open it up.

I learned about this from a talk given by one of the authors. The guy next to me asked, "If you open up the blood-brain barrier, doesn't that mean nasty things can cross, too?" and the author was like, "yep." There are definitely risks.

I'm really hopeful about focused ultrasound for non-invasive treatment of various brain diseases.

Hah, I worked in Kullervo's lab in the early 2010s. It is, indeed, surreal, what you can do with MR-guided focused ultrasound.

ChatGPT. This is the only technology that truly freaked me out in my lifetime (I am 35). It competently explained to me the difference between Dijkstra's algorithm and A* in a psalm-like poem [0]. It was able to find misspelled words in a long text I just made up, list them in alphabetical order, and explain to me why I misspelled them. It correctly simulated a ChatGPT instance which was accessible via a HTTP API, and it correctly simulated a Linux machine on which this simulated remote ChatGPT-API was accessed via curl. It was able to give the responses in XML, JSON, CSV, and other formats, and it was able to simulate Linux tools like cut, grep, sort, awk, jq, sed and others. It was able to add an additional layer of a ChatGPT simulation without problems. It was able to do entity recognition in a long text I provided, and was able to list the entities in a table, with the correct wikipedia article and a summary of the article as columns. It was able to do rudimentary public transit route planning in my home town in Germany (in the form of: go the XY Station, trains will run every 15 minutes from there to the main station, from there you will have long distance lines to Z, etc.), with an apology that it does not have current schedule data for Germany and I should visit bahn.de for better results. When it failed for math questions, it was able to give me Wolfram Alpha queries to find the correct results. It was able to formulate complex SPARQL queries to query Wikidata, run these against the simulated ChatGPT instance via a curl request, grep out some results I wanted, and list them in tabular form with corresponding Wikipedia articles.

All of this in one session, as part of a pleasant conversation, basically indistinguishable from a conversation with a real human.

  > Could you explain the difference between A* and Dijkstra's algorithm in the style of a Psalm?

  < Sure, here is a Psalm-style explanation of the difference between A* and Dijkstra's algorithm:

  Hark, ye seekers of the shortest path,
  And listen well to what I say:
  There are two algorithms that ye may use,
  To guide ye on your way.

  Dijkstra's algorithm is a general one,
  That can be used in any case,
  It explores the graph from the source node,
  To find the path with the least amount of space.
  
  But A* is a more specialized tool,
  With a heuristic function to guide,
  It searches more efficiently,
  And helps ye reach the other side.
  
  So choose wisely, oh seekers of the path,
  And let these algorithms be your guide,
  For they will lead ye to your destination,
  And help ye avoid the pitfalls on the side.

It's an incredibly striking piece of technology and really shows which way the future winds will likely be blowing. A particular exchange I had with it left a mark on me, in which I requested it to behave like a used car salesman attempting to close a deal with a hungry customer. It proceeded to repurpose idioms, make dad-jokes and sling double entendres about the shared joy of cars and hamburgers and how they both are simple, dependable and iconic in my way of life. I sat there for a minute reading over it, nearly in disbelief.

I can accept a system such as ChatGPT synthesizing from data it sucked in, making educated guesses and so on. But to see it do such lingustic gymnastics with a very non-concrete request was humbling. It's given me a lot of pause about the way I absorb digital information and the varying degrees to which I have implicitly assumed the reliability of that information; site A slightly more trustworthy than site B, et cetera. To me, that old trust heuristic I relied on, one I have honed thanks to unfettered broadband for two decades, is now completely upended. It probably has been for some time to be fair, but my time with ChatGPT really cemented that feeling.

Every freshly written statement that comes to me through an internet connected device now gets a side-eye by default.

I've been talking about this for awhile now, but I used to run a marketing service that streamed all reddit content in real time and did text analysis and bot detection. It's definitely a rough estimate but about ~65% of text content was determined to be a bot. I am entirely convinced that there are large entities (political campaigns, nations, etc.) that are using bot networks on social media sites like reddit to simulate "consensus" in online discussions and thus gently sway public opinion.

>I can accept a system such as ChatGPT synthesizing from data it sucked in, making educated guesses and so on

On that note I find it interesting that this has sometimes been an argument to dismiss chatGPT as "non intelligent". What are we if not statistical machines, synthesizing from the data we've sucked in over our lifetime?

I certainly can't see us humans as anything other than that. But if that's true, us human machines seem to have a large number of "low level programs" running in the background that serve to blur the boundary between us and the machines we build and help us to elevate ourselves to a special typing in the universe that very well may not exist.

I feel I think too much about mundane things and sometimes about wondrously confusing things often to my detriment. And at least a few times a week I would swear I run into a person with the opposite problem. Their behavior, choices, preferences. Their thought processes (at least what they share with me) come off as closer to machine than human.

Something in my gut tells me we are more similar to some of the things we build than we might care to admit.

> What are we if not statistical machines, synthesizing from the data we've sucked in over our lifetime?

Reasoning machines who are actually pretty bad at statistics.

That's wrong. It's poetic, but incorrect. These tools are about as good as a non specialist with time to undertake some bullshitting.

> These tools are about as good as a non specialist with time to undertake some bullshitting.

Even if you are right, you still acknowledge that ChatGPT is on the level of a non-specialist bullshitting human you can have a meaningful conversation with. This alone would be enough to freak me out. If you would've told me that this is possible 10 years ago I would've called you crazy.

Subjectively incredible; objectively questionable.

This is my exact problem with ChatGTP, it looks great when you don't know what it's talking about, but as soon as you do, it looks foolishly over-confident in it's answers which are very clearly wrong.

I believe the data gets trained by human rankers, and it should therefore regress to their mean. That said, if they train it to seek approval, I suppose we could teach it like any other student.

Not much worse than a number of people I've talked with, to be honest.

which are very clearly wrong

but not always; And that's what makes it scary. You know people will use it and trusting it.

I think it captured the essential difference between the two algorithms, i.e. the heuristic, so I don't understand how this is 'bullshit'.

I did read somewhere that in some tests, ChatGPT-generated MBA papers got better grades than average MBA students.

Well suited for more most walks of life actually where BS reigns supreme :)

They blocked people from generating performance reviews so at least some were trying.

"confidently wrong"

That's chatgpt right now. To get it to confidently right will take years and years more

I saw dallE and GPT-2 demos and though 'oh pretty cool' about a year later we've got stable diffusion that can run on phones and ChatGPT which can remember context. I thought these things would be 3-5 years out or more. The speed of development is so quick, I think confidently right LLM is around the corner

In less than a decade, I believe front line support chat support jobs and even graphic artist jobs will be made obselete

In less than a decade, I believe front line support chat support jobs and even graphic artist jobs will be made obselete

We can finally get the eighty hour long book-accurate Lord of the Rings adaptation we deserve.

But seriously, I can't wait to feed a novel into one of these things and get a comic book version in return.

The wall of content and interactive exchanges that will fill the internet from chatgpt generated things will become harder and harder to wade through or evade.

I agree that the output is often wrong despite looking right, but in this instance I don't see anything wrong in this example.

> I don't see anything wrong in this example

It's not in the style of a psalm.

Dijkstra's cannot be used as generally as described. A-star can potentially be more general, but that's highly dependent on heuristic. Dinkstras is a-star with a "min weight on shortest path first" heuristic. Because a star doesn't expand shortest paths first necessarily, it cannot necessarily find the shortest path to any node except the prescribed endpoint. Dijkstra's will find all shortest paths with cost less than the path to the endpoint, and that's helpful sometimes.

What is your definition of "general" here? The classic shortest path problem (which the psalm addresses) is described as finding the shortest path between two nodes, and given non-negative edge weights, Dijkstra's algorithm is perfectly general here. It will find such a shortest path in any graph, no further restrictions.

For A*, everything depends on the heuristic, as you said. If h(v) = 0, A* is equivalent to Dijkstra's algorithm, so potentially, it can be as general. But the wrong heuristic (inadmissible, inconsistent) will lead to wrong results, and so calling it a "specialized" tool is correct. The heuristic gives you a specialized version of Dijkstra's algorithm which is faster on specific graphs.

> Dinkstras is a-star with a "min weight on shortest path first" heuristic.

I am not quite sure what you mean here. Dijkstra's algorithm is A* with no heuristic. I am not sure how a "shortest path first" heuristic would look like - do you mean that Dijkstra's algorithm chooses the node to expand next based on its shortest-path cost to the target t? Even if you would construct such a heuristic h(v) = c(v, t) by explicitly calculating c(v, t) each time, this is not what Dijkstra does, as it would basically be a perfect heuristic - you would then only visit nodes on the shortest path.

If you meant that Dijkstra's algorithm is A* with a "neighboring node with shortest path from start node first" heuristic, that's also not strictly true, because expanding the nearest node first is already built-in to A*. A* does not chose the next node v with the smallest h(v), but with the smallest g(v) + h(v), where g(v) is the shortest path cost from the source node to v.

> Dijkstra's algorithm is a general one, That can be used in any case,

I take issue with this statement. "any case" implies it's more general than A star, which is not true, it's a specialization of A star with (ok you win) h(v) set to nothing. It necessarily cannot solve as many problems as a star.

And Dijkstra's won't work in "any case" at all, esp graphs with negative edge weights.

The explanation struck me as glossing over too much, to the point of being misleading. Perhaps I'm being too pedantic, fine, but a more enlightened comparison would read more like our discussion than what was given.

You realize it had the constraints of a poem, and needed to take some liberty with description there?

Sure sure. I'm being pedantic. But replacing two sentences would fix it.

I actually think the robot's poetic take matches my thinking more closely than this description

Edit:

I guess in this description dijkstras is more specific, in that dijkstras is the specific instance of A* with a zero heuristic.

But I think what HAL over here was saying is that you can use dijkstras in a superset of scenarios in which you can use (non-trivial) A*, so in that sense dijkstras is more general than A*, so it's not wrong.

> These tools are about as good as a non specialist with time to undertake some bullshitting.

You’re not wrong, but AI being passably good at bullshitting (while mostly keeping a rhyme/meter) is still mindblowing to me.

It's an amazing accomplishment technically, and that deserves to be emphasized, but it is still not producing reliable outputs.

Subjectively incredible; objectively flawed.

Humans, in my experience, have even more reasons to be flawed than the AI. Yes, the AI can be incorrect, but humans can be misled in what they believe the same way, and have the added problems of ego and misaligned incentives. Heck, in this very thread we have one human calling out another for being incorrect about whether or not an AI was correct. Locating sources of reliable truth is an unsolved problem AFAIK.

Also psalms don't rhyme, even in the original Hebrew. Also even if it is supposed to be a poem with rhyme and meter, ChatGPT's poem doesn't have correct meter.

Agreeing with you. Psalms typically employ parallelism not rhyming. Two examples:

  The sun will not harm you by day,
      nor the moon by night.

and

  My life is consumed by anguish
    and my years by groaning;
  my strength fails because of my affliction,[b]
    and my bones grow weak.

'poetic': you have described it accurately. I fail to see what the hullabaloo is all about. Call me jaded.

It is passing medical exams and will be used to help diagnose issues with similar reliability as humans.

That can only be possible in a limited set of cases where the inputs necessary to make a diagnosis are all present in the patient chart. Human clinicians rely on other inputs to make most diagnoses including visually looking at the patient from multiple angles, asking them questions, manipulating and feeling the patient's body, listening (with or without stethoscope), and even smell. We are a long way from the robotics and sensor integration technology necessary to automate those steps in the diagnostic process.

Agree- so many are dismissing it because its not perfect, but this is an absolutely enormous leap from anything else I have seen in my lifetime, and this crosses the chasm IMHO between "AI is unlikely to really be able to have general applicability" to "AI is probably going to upend life as we know it in our lifetimes."

Maybe it will just peter out at this level like self driving car technology did, but I really doubt it, and it seems to me that the building blocks are already there to commercialize this and use it in a real way. The future is going to be interesting...

ChatGPT is smart enough at the first prompt, but what really stands out - freakily, I might add - is how it can remember earlier data. You can go several levels deep and it will still reference the first answer and contextualize it properly.

"Do X" is great. But "Now change X to Y in the style of Z" is what blows my mind.

Thats interesting. When I did play with it a bit, it wasn't clear to me if it was actually doing that, but in hindsight it definitely was and was not just a coincidence. When I first used ChatGPT, I had a dog that recently passed, and she had such a big personality (a mischievous always hungry hunting dog) and was just very different than my other dog (a pitbull mix that likes to guard things), and I had thought that the two of them would be a good basis for a children's book.

I initially put in a prompt like "tell me a story about the hunting dog and the guard dog." and the results were pretty meh. I was interested to see if it was actually pulling in data from FB so I put her name in instead (she had an FB page yes). It did not seem to do much. So I put in some things like "the little hunting dog is always hungry." "the hunting dog is always looking to hunt" and then did a fuller prompt of "the hunting dog and the guard dog are going to the park. tell me a story about it" and finally got a very good fully fleshed out story about how the little dog was on the prowl for a squirrel while the guard dog watched out and it was really well written and made about as much sense as a fictional tale could. There was no awkwardness or other tells that would have made you think that this was written by anything other than a human.

Anyway, that is huge that it can do this. I do remember when I used to play with other chatbots that remembering past context was something they were unable to do, at least not well, but in most cases it seems they didn't even attempt to. ChatGPT has blown me away in many ways, but this is a very specific leap forward.

One of them I used was supposed to be 'pick-a-path' style fantasy fight the dragon sort of thing. I decided to throw the A-Team into it. It integrated them in and even knew the correct names and their context of what each char tended to do. By far not perfect. But the fact it could do even 'kind of' that. Is very interesting. 'kind of' is for some things is perfectly fine. The generated art ones are very interesting too. It reminds me a lot of early emulation discussions. Where people were arguing unless you had cycle perfect emulation nothing would work. Turns out 'kind of' close works for like 95% of the cases. Some things did need that sort of detail. But most didnt.

Ought to be "to guide you on your way", "helps you reach the other side", "for they will lead you", "and help you", since "ye" is the plural nominative (not accusative).

I grew up using archaic, Jamesian English regularly (in a religious community), so it always sounds wrong when people use them incorrectly while attempting to be old-timey, which is a bit distracting and ruins the effect.

Apparently ChatGPT suffers from hypercorrection as much as any modern speaker.

(The meter is also dreadful, which is another thing that I think many modern English speakers don't often do precisely.)

RE: chatGPT ...

There was an "ask HN" a week or so ago about knowing how your personal machine was or was not compromised ...

I am imagining training a model on all of the PDFs and email and receipts and contracts that I have spent the last 30 years protecting ... and then exploding my home directory with 2M parallel copies.

Now what ?

Which is the real correspondence ? Which contracts are real ? Which invoices and receipts ?

Could one construct a framework where all data at rest is worthless and only witnessed transactions and traffic have any surveillance value ?

Yet it will happily tell you random non sense with utter certainty like that it takes twenty minutes to boil a whole chicken in the middle of a recipe or listing an incorrect number of children with fake names while writing a biography.

That's not even close to the style of a Psalm. It's still pretty cool though.

A few months ago, I would have said Stable Diffusion, but ChatGPT wins, hands down.

We're living in exponential times.

Which metre is that supposed to fit? I can't fit that around any psalm I can think of, most of which are 8/6/8/6 metre.

Shhhh. Just more bullshitting from the computer bullshit machine.

could you provide some examples of your prompts leading to simulation of Linux within ChatGPT?

I agree, it’s amazing and it’s just the beginning. When this get numerous iterations of improvement and is distributed at scale and integrated with everything it will power the next technological leap forward. This to me is obvious.

Unreal Keanu: https://www.youtube.com/shorts/FeHzQizPDNg

people in the comments have no idea it's a deepfake. Without knowing beforehand, I wouldn't recognize it too.

Looks completely fake to me. The face moves very unnaturally and doesn't even stick to the body properly. It looks like a super realistic mask (meaning it has many of the same problems a mask has).

I was about to downvote you until I read your comment after watching the video.

This video leads me to believe that there will soon be a time when popular people will just pick some pre-made advertisements. No need to go and film it since that has already been done without that person. We'll then accept deep fakes as a valid marketing strategy (or whatever purpose may come up), until some protests require them to be watermarked.

I love Keanu, but he’s sort of “easy mode” for a deep fake, isn’t he?

In fairness, Keanu Reeves, like Kristen Stewart, isn't the hardest person to deepfake…

Is this because both are actors and therefore there is lots of available training data? Or something even more specific to these two people?

Wow - they raised $100 million. They're expecting people to pay $33/mo for the service, which includes the grinder/dehydrator bin, plus the cost of mailing the dense milled organics back to their processing facility.

Figure that actual physical expenses cost $18/mo, leaving $15/mo profit per household; on top of that, they'll have extensive marketing costs - let's say marketing & employee costs take another $10/mo, leaving $5/mo profit per household. That means they'd need 1.6 million households to subscribe for a year just to get their investors their money back, or about 1% of the potential market.

How did they possibly win over investors? If I could short this I would.

> How did they possibly win over investors?

Low interest rates have shifted massive amounts of capital to vc. We’re talking trillions possibly, including sovereign funds and ultrabillionaire family offices.

Are those wealth and investment managers nuts? Maybe, but I’ve concluded the most likely explanation is that they know exactly how to play the vc game: place a number of wild bets and hope that one in a hundred pays off. They sometimes seem to barely do due diligence, perhaps for efficiency and speed in allocation, and because the vc portion of their otherwise well-diversified portfolio is tiny. You and I get to partake in the schadenfreude if these stupid ventures collapse but they’re wiping their tears with the returns they make on other asset classes - stocks back then, fixed income now, etc.

If interest rates go back to the “old normal” for a sustained period of time then maybe this ends, but maybe the new normal is here to stay. We’ve been told there’d be a big cleanse of stupid or otherwise unprofitable ideas (can we really cram more SaaS solutions into every single niche under the sun?) but I’m seeing very little of the sort, other than layoffs and downsizings which are not thus far commensurate with the fireworks we were promised.

> the most likely explanation is that they know exactly how to play the vc game: place a number of wild bets and hope that one in a hundred pays off.

But isn't a key point of this theory of investing that you invest in many companies that have a 1% chance of making a 100x return - rather than investing in companies with a 0% chance?

Paid composting collection sounds like a ridiculous idea but if for example they manage to become a standard and get monopolistic contracts like waste management companies, on a national level… there’s your moonshot. Here, have a hundred mill.

It's true, but the raise _just happened_, which means there's still loose VC money out there. The narrative has been that there's been a transition to more conservative funding...apparently not in this case, at least.

There’s usually a lag… raise might’ve happened >1 year ago.

I'd pay $100-200 for the trash can thing. There is a company making a smaller one, with the idea that you toss the output into your own compost pile. It cuts down on odor, rodents and time to compost completion.

What happens to the trash can if I stop paying the subscription fee?

(Fast forward a few years, and someone will rewrite the above as a postmortem.)

We have a Vitamix Foodcycler [1] we got on sale. It works well but the cycles take a while and it doesn’t process that much at once. Honestly we just went back to using a counter top bucket and then putting it in our municipal food waste bin.

Austin turn all that stuff into compost, and then give it away to the community (just turn up with bags) and I assume use on city run parks and so on.

[1] https://www.vitamix.com/us/en_us/shop/foodcycler-fc-50

Honestly if you have a big enough pile, just bury the waste in the compost. Or get a Green Cone Solar Digester, I've literally put hunks of meat & coconut husks and it just disappears, no rodents, no smell. I was putting buckets of compost in there every week and it would just melt into the earth.

I used a local version of this type of product in a city I used to live in.

Main positive is as you mentioned, food waste smell is gone, and no rodents/animals in the trash either inside or outside.

There is the part where they expect to earn back from reselling the compost.

> Mill has partnered with two processing facilities that purchase and turn all this dried food into a chicken feed ingredient, filtering out any errant forks or inorganic materials that accidentally get tossed in the bin.

The bit about filtering out inorganic material seems a little too convenient to gloss over though.

As a kid who grew up on a small (by Norwegian standards) dairy farm I remember it confused me that food waste couldn't be sold to farms.

As a grown up, seeing all the stuff people put into food waste I can understand it.

What I still can't understand though is how many people mistake food wrapping for food..!

Agreed.

I am a compost consumer and I have no desire to plasticize my pastures and fields the same way we’ve filled the oceans with plastic.

You can see this for yourself: just go to Home Depot and buy a bag of dirt … it’s not even micro plastics … whole objects like ballpoint pens and so on.

> ...how many people mistake food wrapping for food..!

It isn't mistaking, it is not prioritizing the cognitive load for the separation effort. When I was in Japan, I was impressed with the level of fastidious compliance I witnessed in materials separation. That convinced me the talk in the US about how mainstream households could not possibly support a comprehensive cradle-to-cradle materials handling infrastructure are really talking about culture and/or necessity and not logistics.

"... I was impressed with the level of fastidious compliance ..."

Diversity is neither good nor bad - it just has benefits and costs.

You witnessed one of the costs.

On the other hand, we invented jazz and snowboarding. Those are examples of benefits.

I've made my choice.

I paid around that much to have my compost picked up from my apartment weekly. They would drop off a reuseable bucket for the upcoming week and pick up the bucket from the previous week.

How did you figure those numbers? They don't seem related to any of the content in the article or any other content I can find about them online.

We should not be mailing compost around...that sort of defeats one of the purposes. There are local composting companies/orgs in most major metropolitan areas. Mine is Compost Now.

Sometimes (often these days) i can't tell if these things are parodies or real products. It reminds me of Juicero: https://en.wikipedia.org/wiki/Juicero

In Europe many countries have specific trash bins for food waste, they're collected by the city and reused for compost and biogas. No subscriptions, no investors, no soon to be e-waste wifi and bluetooth connected trash can, no shipping dirt in box

Some of their assumptions seem to be very much US based where "green bins" for garden and food waste might not be a thing? I don't know but where I live in Canada, contents of the green bin definitely don't end up in the landfill like they say. So it's not even a problem that needs solving in many other places.

AVE did a great teardown of one a couple years ago, impressive machine with a stupid purpose.

In the US too, plenty of cities (even small ones) offer compost collection as part of standard trash and recycling collection.

It would be interesting to see an environmental impact analysis of use of mail vs a compost cycle that’s does not use mail. Find it hard to believe they’re reusing the labels, boxes, plastic wrapping, etc too.

I think the impact analysis should be between a compost cycle that uses mail vs no compost cycle, because I would imagine that the alternative to this is just throwing food in the trash for most people

Blows my mind that that's a thing. If it's urban, how is there no compost bin system. If it's rural, just have a compost bin outside. It's like people don't know how to live anymore with every part of their lives being handled by some shitty subscription service. Food, waste, what's next, a box you can ship your poop in that's 39 bucks a year?!

Possibly, though there are plenty of high-density urban areas that require separating compost materials and pick it up with trash, recycling, yard waste, etc. — so to me that would seem like a better comparison; or just compare all options.

We should normalize having chickens in the office.

No. Have you ever raised chickens, or cleaned out a coop?

Ha! I actually run a company that does Coop cleaning, babysitting, coop set up, day old chick delivery, etc. We're launching the world's best Coop in 45 days, stay tuned :)

Although it sounds funny, this is actually kind of a serious question: are you concerned about an egg bubble?

FAANG companies probably have enough money for additional space and employees to look after the chickens

I don't think this is very practical. It would cause too many communication issues in the agile process.

Things like this make me realize how poor the rest of the world is, and how wealthy America is.

Here in Germany we have to split our garbage and one "bucket" so to speak is compostable and gets taken by the regular garbage trucks and I assume is composted in large facilities. That seems like a more reasonable approach because it scales to a whole city doing it

Here in Saint Paul, Minnesota, USA, they are planning to ship compostable plastic bags to homes, which you can use to put organics into the normal metal/paper/plastic recycling stream. Those bags get picked out at the recycling center and used for compost to sell to local farms/etc and (hopefully) at least pay for the program, and maybe even bring in some extra funds. No extra cost to users or hassle mailing packages of garbage (lol).

> compostable plastic bags ... normal metal/paper/plastic recycling stream

That's really clever since it avoids needing to have separate trucks.

Will they also accept leaves and yard trimmings? These are much larger in volume, so I'm not sure if they could be handled, but maybe with large bags it's fine.

> sell to local farms/etc

My city sells to farms and also sells it in bags at retail stores. It's meets standards that are supposed to make it safe to use in your backyard garden.

Also, since it costs money to put stuff in a landfill, and since this diverts from the landfill, it saves a bit of money that way too.

(Further info: https://www.austintexas.gov/department/dillo-dirt)

Same here — I live in Eastern Canada and my municipality is rolling out a program where you'll put compostables in a separate bag, but the sorting is done by the trashman.

And then the yellow bags for plastic, which they take to SE Asia on the otherwise empty container-ships, so that it gets dumped on a beach or into a river, while Germany fills its quota for recycling.

Sorry for the cynicism, this was the case a few years ago, maybe not anymore?

> this was the case a few years ago, maybe not anymore?

I'm not sure what happens with the plastic in SE Asia, but we still send most of our plastic there.

https://de.statista.com/infografik/25368/wichtigste-abnehmer...

Bullshit.

This statistic is listing the share of exported plastics that are exported to certain countries. But that's not "most of our plastic", because overall exports are around ~10%. So "most of our plastic" is either recycled or burned within Germany. (Not saying any of this is ideal, but it's not helping to spread false information.)

I apologize. I chose poor wording to the point where my sentence it is becoming untrue.

I meant something like: “The majority of plastic we export to other countries is still being exported to SE Asia”.

As the other comment said, it's more likely that they get burned.

I think it happened that due to waste reduction, "normal" garbage is sometimes not enough to keep the furnaces running, so they take recyclable material from the yellow bags and burn it, to keep the temperatures stable...

This definitely happens for plastic. But food waste does tend to actually get composted.

I don't see what you are trying to say here? That we shouldn't even try to recycle anymore because some garbage gets shipped to SE Asia?

not sure if it qualifies as technology:

- nicolas schabanel team works on molecular DNA programming, they had game of life capable structures made of DNA tiles. The mentioned being capable of transpiling tiny lambda calculus expressions but were stuck (this was in 2013~) due to thermal degradation on long programs. His courses are on dailymotion.

- michael levin morphogenesis / developmental biology research: dude revived 50s~ ideas with gap junctions and cell levels "information processing" .. he ended up regrowing a second head on a larva after reprogramming cell messaging to alter the natural regeneration process. He was in a lot of interviews/podcasts in the last months.

I truly feel there’s going to be some kind of industrial revolution with DNA or derivative based manufacturing.

A lot of trends are showing nanotech reaching mainstream. Just two days ago there was a veritasium video about gecko skin like thin film that could hold smooth objects passively.

Seconding Michael Levin, that guy is doing some incredible stuff

It made me feel something very very new, a blend of infinite "power" at reach and at the same time something that could really break sanity and ethics forever.

It definitely comes straight out of sci-fi at least. In the original Deus Ex, I think when you first break into the Versalife offices in Hong Kong, you can overhear an employee talking about their universal constructors (basically 3d printers that work at the atomic level). The employee mentions one of his friends created Conway's Game of Life with buckyballs.

Edit: nevermind it's a Versalife employee at a nearby bar/club, not in the offices themselves.

Seeing a dude grow human neurons directly connected to a computer chip to make a "human AI", all from his garage [0]. It showed me what is possible with science these days if you have enough dedication and know-how. Made me feel deeply excited and scared for the incoming future.

[0] https://www.youtube.com/watch?v=V2YDApNRK3g

The thought of clandestine modding labs and neural implants brings to mind a future similar to Ghost in the Shell.

At this point I feel like people must also be trying to modify their DNA in secret. I wonder if we'll hear some horror stories in the next few years.

One of the few YouTube channels that i can identify by the experiment alone.

Oh yeah this one... This really disturbs me. I can't shake the feeling that it might be conscious somehow; trapped, enslaved and tortured like some kind of Black Mirror episode.

Probably not a lot. Babies when they're born have billions of neurons but believe me, there isn't much going on yet :)

This is why I give that engineer at Google a lot of slack for his concerns that Lambda was conscious.

There’s a bit of an imperative, in my opinion, to over-index on that concern, because we could be building and torturing things for decades because people are afraid of losing their jobs.

Fair enough, it does make sense to have a higher tolerance for false positives than false negatives in this domain. I think that's a hard thing for people to accept though since so far it's been very obvious the objects and systems we interact with have not been conscious (except to pansychists of course.) It might be good to get practice in and build the habit early though, even if we don't think these current systems are conscious.

Exactly. In the instance it doesn't seem warranted at all, but at some point we will have to accept 'whistleblower' type accounts of the same nature with a bit less excoriation.

Some of the VR movies are getting quite good. First the newer generation headsets- 2K, 90+ fps, cableless- no longer induce nausea. Second, movie makers are becoming versant with the strengths and limits of this media.

One I saw in December called Container, I felt I was in the room with various scenes of realistic 3D people.

The motions on the recent Boston dynamics demo video were eerily realistic and humanlike. Sure preprogrammed but still that smoothness stood out to me as something new

It's interesting to see both the advances in humanoid robotics and language models like ChatGPT. The obvious next step will be to combine these two to achieve a truly human-like android, just like in old school science fiction.

Of course, bridging the uncanny valley to make it even look passably human is another milestone entirely.

The ability for the robot to move in multiple directions at once… bending knees and arms and waist at the same time, threw me for a loop.

It's about gecko tape, tape that imitates how a gecko's feet adhere to surfaces. By Veritasium, FYI.

I've been seeing videos about this for probably 20 years (here's a link from 2009 https://phys.org/news/2009-06-gecko-feet-advances-science-fr...). But it's starting to seem like an elusive graphene-type material that will never be commercialized :(

When can I finally buy some gecko gloves, damnit!

"Petmiglia" - a 360 degree automated pet drying chamber I came across at IFA. If your dog is scared of a hairdryer, why not put him in the hairdryer?

http://en.petmiglia.com/

Surprised they just didn’t combine an automated washer with it to make it full service.

*pet drying chamber, in case anyone else was confused. Definitely surreal.

The Mobility Scooter craze. South Park nailed it. One day there were a couple scooters and you went oh interesting. A moth later there were thousands clogging every sidewalk with no discernible method of managing these devices. Then just like they came they were gone.

How many billions spent? How much e-waste was generated?

Mobility scooters are the things disabled people ride. There should be a term to refer to these electric, Razor-style form factor scooters, but I think they are just pushing the Vespa-style scooters (many of which are also electric) into the term moped and taking the term "scooter" for themselves. I call them kid scooters.

Unfortunately it's still a thing almost everywhere in EU.

Unfortunately, the EU country I live in does not allow them.

And that is unfortunate, because whenever I visit another EU country I find them very useful.

I doubt many people would argue against their usefulness. The problem is management of the scooters when not in use.

Even out in the suburbs, the local sidewalks have them discarded haphazardly. Not in a charging stand, not in a group, just ad hoc lying across the sidewalk. The bike share has dedicated stands for groups of 10-20 bikes - this makes far more sense to me than users just dropping them in the sidewalk or street when they're done riding.

If you're an older pedestrian, or otherwise mobility challenged (but able to walk), they're a nightmare.

I think we're well past the craze curve. I see way less scooters nowadays. Somewhere there is a mile high mountain of old scooters.

Gecko inspired sticky tape which is so strong (and yet non-sticky) that 4 of them lying on a curved surface can pull a car.

Veritasium video https://youtu.be/vS0TuIPoeBs?t=640

The availability of different peripherals on smartphones.

The first time FaceID succeeded in the dark, with my grizzled, bearded, asleep, partially obscured face I remember the flicker of amazement that I used to feel all the time thirty years ago when everything was new.

I sometimes think about my phone the way I think about a blank piece of paper before I write in it, just the sheer magnitudes of magnitudes of possibilities inside it’s tiny little electric chassis.

The power of my phone rivals total computing power of industry giants just a few decades ago, huge computers that people built large container rooms for, poured over schematics, organized millions of dollars for.

For what I make in a month, I could have more than a dozen of my iPhone just laying around if I wanted to. Half the size of a proper table coaster.

Also, SIMD. Like, wow. That was a brainmelter when I learned about it. I’m not quite punchcard programming old, but all the people that I worked with when I started would talk at length about it. Now you can just vectorize… whatever… basically for free.

I mean, is there really any question? There is only one answer. Okay, maybe two. Stable Diffusion and ChatGPT.

Lot's of surreal stuff out there, but these two ... there is no question. Not one.

Living in exponential times.

I was yesterday reading about Transcranial Magnetic Stimulation. The effect sizes this method is achieving for relieving a bunch of mental illnesses are extraordinary. This is going to revolutionize psychiatry in the near future.

Spatial Transcriptomics. Being able to see gene expression at a resolution of a handful of cells in a cross section of tissue is revolutionizing disease research. https://www.nature.com/articles/s41592-020-01033-y

Cool I work in spatial transcriptomics, it's still early days but not too far off we're going to get great resolution and great capture. Especially for the brain, and maybe even tumor micro-environments it could be really cool

Would be super curious to hear Sam’s response to that video given it claims that it’s impossible for it to be a clean reaction, which contradicts statements I believe have heard Sam make about it.

Worth nothing Helion has raised $577.8M of which $375M was provided by Sam Altman.

CRISPR gene editing. Rewrite every instance of your genome in situ. And you not only survive but thrive, unbelievable.

I remember hearing about an GAN-based tool that would transform clothed pictures of women into nudes. That was depressingly surreal.

The fact that somebody making this feels like an inevitability is just incredibly depressing. I mean, sure, it's just a fake AI guess, but Jesus Christ come on :-/

The whole industry of carbon sequestration is surreal. It's a completely useless technology except for proving to someone else that you've affected the inputs to an equation to some degree.

I guess the jetpak demonstrations where they actually seem realistically usable are very cool

LTO Tape drives that run their cooling at 100 percent power when idle and have no particle filters https://news.ycombinator.com/item?id=34502596

This isn't that uncommon in datacenter hardware. Most of the gear does not have filters on intakes. The air should already be filtered in the facility anyways.

Running fans at 100% is slightly weirder, but also not unheard-of.

Not saying this isn't true, but you made the thread and the video. Is there anyone else talking about this?

most things don't have filters.

I don't think I've seen a drive failure because of it though. I think the last time the robot failed it was mostly because of the autoloader not working properly.

Tape drives (3592) in a Singapore data centre had lots of problems in the smokey burning season until they put in filtering specifically for the drives. In other office-like data transfer rooms in other cities they didn't seem to have problems, so perhaps there's something especially bad about smoke.

Tape drives need to be disrupted. They are way too expensive.

AI nsfw bf/gf apps. It probably just makes sense to this generation but for me, it feels like something out 90s era sci fi.

And Blade Runner 2049.

And Star Trek TNG, with the holodeck (LOL, friggin' Riker)

A bunch of other stuff if ones with robotic bodies count. Star Trek: TOS has some. Fritz Lang's Metropolis (1927) features a robot re-creation of a character's dead lover. Though that's a bit different than one simulated without a reference.

I think Replika (https://replika.com/) is one of the bigger ones. I know of it from a few youtube videos making fun of it, but I really don't know how anyone can form an attachment to a chatbot.

Without a doubt ChatGPT. Still surprises me daily.

To piggyback, it's been almost a year and I still haven't gotten over the first time I saw DALL-E 2. Or the first time I've used GPT-2 (via AI Dungeon Google Collab sheet). Not sure when was the previous last time I've felt that sense of wonder. Perhaps the first time I've interacted with the original iPhone?

Edit: I remembered some more from the past:

- First Boston Dynamics Atlas videos.[0]

- First successful Falcon 9 landing[1].

- A video explaining how the Curiosity landing will be done and then watching the stream when it happened.[2]

- The concurrent landing of two Falcon Heavy boosters on land.[3]

[0] https://www.youtube.com/watch?v=rVlhMGQgDkY

[1] https://www.youtube.com/watch?v=ANv5UfZsvZQ

[2] https://www.youtube.com/watch?v=h2I8AoB1xgU

[3] https://www.youtube.com/watch?v=sX1Y2JMK6g8

First time I got the "there's something special happening here" vibe was seeing the early "hallucination" images some years ago. Some examples here: https://www.businessinsider.com/these-trippy-images-show-how...

My wild guess for the next 5 years is that we'll have Stable Diffusion with the ability to create NeRF scenes.

I wasn't able to realize the scale of the shift that's about to happen back then.

I just remembered another example of hearing about something that seemed like pure magic:

Reconstructing what a person is seeing out of their fMRI scan (2011): https://www.youtube.com/watch?v=nsjDnYxJ0bo

That’s most interesting aspect to me is that 100s of thousands of people were all likely aware of the developments in the field, but few actually knew what was coming down the road in the near future. It’s these types of gaps I find the most interesting when looking at technologies like this.

I'm right there with you. Google's DeepDream I think?

That first week of DeepDream images flooding the web showed me that someone had snuck a can of worms onto the table, and while they had graciously not opened it immediately, they had maybe cracked the lid just a bit

ChatGPT. I'm 33 and first time I've ever truly been blown away.

It's been really valuable as well not just a novelty. I'm certain it will change almost every aspect of our lives, starting with our children and how they learn in our current education pipelines. The bubble don' popped!

Deep fakes certainly hit me wrong. Especially given how easy it is to do to celebrities.

It started off with mundane stuff with a great message: https://www.youtube.com/watch?v=cQ54GDm1eL0

Then South Park guys, Trey Parker, doing absolutely hilarious deep fake video. They make Al Gore and Trump say poop. https://www.youtube.com/watch?v=9WfZuNceFDM

But then basically the same time I saw deep fakes presented as true. Trump saying dumber things than normal. Biden appearing like he has late stage dementia. None of it true. As an outside observer of american politics... pretty damned concerning.

But then I read a real statistic. 95% of deep fakes... are to make fake porn. Women who have never done porn now have tons of porn made of them. Worse yet, you can't do anything about it. You dont own the copyright. There is no copyright infringement. You cant sue for royalties because they assert its not you and you never did porn.

So the USA/DHS decided they would try to police this. Try to get this all under control. They proceed to put a registered spy in charge of it who only policed 1 side of the aisle.

So this technology is destabilizing the USA and heading directly toward... https://en.wikipedia.org/wiki/Second_American_Civil_War

Thanks for the tip and it does look good but I seem to be watching paw patrol and blippi lately and nothing at all I want to watch.

The great thing about perpetual motion machines is that you don't need to spend a lot of time digging through all the details, and you don't even need to be well-versed in physics, to understand that they're impossible. You just have to know that energy cannot be created or destroyed.

Two items of note from their FAQ:

> "Except for the usual forces such as mechanical friction, resistance due to air, etc., no major force opposes this movement to the point of canceling it. "

Yes, and those "usual forces" require additional energy input to overcome.

> "The correct application of the Law of Thermodynamics (a) refers to closed systems which (b) exist in a reality of which 100% is known and understood. Both (a) and (b) can only ever be true with absolute certainty in theory, but never within the limited perception of reality how humankind experiences it - in other words: How much sense does it make to think that a system which is observed in only 4 dimensions can never and will never be influenced by what is contained and happening in the following 8 (higher) dimensions?"

So they're using magnets to pull energy from other dimensions. Got it!

> The correct application of the Law of Thermodynamics [...] exist in a reality of which 100% is known and understood

Uh, are they really saying that thermodynamics only starts working when we have a perfect understanding of reality, and not a picosecond before that? What the actual duck.

”What does Kryon mean?”

”The correct question would be: Who is Kryon? Kryon supports Humanity in many precious ways - not only by dropping hints about upcoming revolutionary technologies based on magnetism, such as (shallow depth) geothermal energy generation, (mass-scale) water desalination and magnetic engines. You are encouraged to tune in to the neverending stream of new free audio channellings.”

It seems a being from another dimension has blessed humankind with a perpetual motion machine. Where do I send my money?

Perpetual motion and free energy stuff was interesting things to read about back in early 2000’s internet (around the time when conspiracy theories were kind of niche).

The only thing of interest recently has to be the EmDrive [1] - only because the rigorous testing it was put through finally put the mail in the coffin of backyard free energy nuts.

https://en.wikipedia.org/wiki/EmDrive

Does it not seem suspicious to you when you see a video of the device, and it's of a 3d model?